A field guide to AI positions

Diffusion models

Inside a model.

Source is over 18 months old.

Publication dates and source age

Sources counted: 1

Newest dated source: 2020-06-19

Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

Open in the glossary Reading notes · Structured record

Prepared with AI assistance. Not independently fact-checked. Original sources and qualifications are below.

In plain language

Generative models that can build an image through repeated removal of noise. Generating a picture does not establish that the pictured event happened. [1]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-diffusion-models-1a5192ba3d7825ca26b24a72. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

Limits & distinctions

The classic diffusion approach refines a noisy representation over successive steps. That differs from a language model generating text one token at a time; both are computational methods. [1]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-diffusion-models-09422ce4d5c74cb753a9bb98. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

A fuller explanation

In the denoising approach, training examples are corrupted with noise and a model is trained to reverse that process. Generation starts with noise and applies learned steps to produce an output. [1]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-diffusion-models-1e4c26398ee834b2e16dc7b8. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

How it relates to the map

Map context: this is a way to generate content. Its use does not establish a view about catastrophic risk or faster development. [1]

Reference this explanation or suggest a correction

Editorial interpretation or qualification. Claim ID: claim-term-diffusion-models-25f52a21ad9f2e54a62ed1b2. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

Share this page

https://theaiatlas.org/ideas/diffusion-models/

Download a share image · Vector image

Image previews are summaries. Keep the page link so readers can check the evidence.

Sources and what we read

  1. 1. Denoising Diffusion Probabilistic Models

    Jonathan Ho, Ajay Jain and Pieter Abbeel / arXiv · First-hand source · Published 2020-06-19 · Updated 2020-12-16 · Material last read 2026-09-15

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2020-06-19

    Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

    Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

    Read scope is described in the source note.

    No archive check recorded.

    Read the abstract, introduction, forward/reverse process and sampling algorithm. The entry explains the denoising approach in this paper, without treating its benchmark results as current performance.

    Source ID: glossary-wide-diffusion

Edition and machine-readable evidence

Content version 0.20.0. Evidence cutoff 2026-09-15; this does not mean every source was read on that day.

Pinned complete dataset · Complete evidence page · Agent consumption guide